分娩奶山羊躺卧姿态的自动识别及胸腹部运动规律研究

doi:10.12160/j.issn.1672-5190.2025.02.008

畜牧与饲料科学 ›› 2025, Vol. 46 ›› Issue (2): 59-70.doi: 10.12160/j.issn.1672-5190.2025.02.008

分娩奶山羊躺卧姿态的自动识别及胸腹部运动规律研究

冯思远, 安晓萍, 王园, 齐景伟

内蒙古农业大学动物科学学院/智慧畜牧自治区高等学校重点实验室/内蒙古自治区高校智慧畜牧集成攻关大平台/内蒙古自治区草食家畜饲料技术研究中心/国家乳业技术创新中心奶山羊繁育与养殖技术研究中心,内蒙古呼和浩特 010018

收稿日期:2025-01-10 发布日期:2025-07-09
通讯作者: 齐景伟（1967—）,男,教授,博士,博士生导师,主要从事智慧养殖及生物饲料技术创新研究工作。
作者简介:冯思远（1997—）,男,硕士研究生,主要从事智慧养殖及生物饲料技术创新研究工作。
基金资助:
内蒙古自治区科技计划项目（2022YFHH0103）; 内蒙古自治区科技重大专项（2021ZD0023-3）

Automatic Recognition of Lying Postures and Analysis of Thoracoabdominal Movement Patterns in Parturient Dairy Goats

FENG Siyuan, AN Xiaoping, WANG Yuan, QI Jingwei

College of Animal Science, Inner Mongolia Agricultural University/Key Laboratory of Smart Animal Husbandry of Universities in Inner Mongolia Autonomous Region/Integrated Research Platform for Smart Animal Husbandry in Universities of Inner Mongolia Autonomous Region/Forage Technology Research Center for Herbivorous Livestock in Inner Mongolia Autonomous Region/Dairy Goat Breeding and Farming Technology Research Center of National Dairy Industry Technology Innovation Center, Hohhot 010018,China

Received:2025-01-10 Published:2025-07-09

摘要/Abstract

摘要： [目的]运用You Only Look Once version 5s（YOLOv5s）模型实现对分娩奶山羊躺卧姿态的自动识别,并结合Farneback光流算法对分娩奶山羊胸腹部起伏特征进行分析,从而为奶山羊分娩的精准化管理提供技术支撑。[方法]利用YOLOv5s模型对分娩奶山羊的躺卧与站立姿态进行分类识别,采用精确率（P）、召回率（R）及平均精确率（mAP）对模型分类结果进行评价。通过视频识别后,依据分娩时长将20只萨能奶山羊分为2组：A组为分娩时长<30 min,B组为分娩时长≥30 min。并基于Farneback光流算法提取分娩奶山羊胸腹部起伏参数（速度、高度、单次持续时间、次数）,对比分析两组奶山羊胸腹部运动规律。[结果]①YOLOv5s模型对躺卧和站立姿态识别的P分别为98.4%和98.3%,假阳性率<2%,误判风险极低;R为95.3%和94.6%,漏检率<6%,监测覆盖性优异;mAP达96.3%和95.2%,综合性能稳定,鲁棒性强。②光流法分析表明,B组胸腹部起伏速度均值为5.358 px/s,显著（P<0.05）高于A组均值（2.461 px/s）;B组胸腹部起伏高度均值为6.104 px,极显著（P<0.01）高于A组均值（2.280 px）;B组单次起伏持续时间均值（4.687 s）与A组均值（4.272 s）差异不显著（P=0.35）;B组胸腹部起伏次数（45.67次）极显著（P<0.01）高于A组（12.92次）,且节律性降低,这表明分娩难度随分娩时长增加而升高。[结论]YOLOv5s模型与Farneback光流算法协同运作,实现了对奶山羊分娩姿态的精准识别以及胸腹部运动精准量化。该技术能够集成到牧场分娩预警系统中,实时识别奶山羊的异常分娩行为,降低母羊难产风险,为奶山羊的智能化管理提供技术支持。

关键词: 奶山羊, 胸腹部运动规律, 姿态识别, YOLOv5s模型, Farneback光流算法

Abstract: [Objective] To achieve automatic recognition of lying postures in parturient dairy goats using the You Only Look Once version 5s （YOLOv5s） model and analyze thoracoabdominal movement characteristics using the Farneback optical flow algorithm, thereby providing technical support for precise management of dairy goat parturition. [Methods] The YOLOv5s model was employed to classify lying and standing postures of parturient dairy goats, with model performance evaluated by precision （P）, recall （R）, and mean average precision （mAP）. After video recognition, 20 Saanen dairy goats were divided into two groups based on parturition duration: Group A （parturition duration <30 min） and Group B （parturition duration ≥30 min）. The Farneback optical flow algorithm was used to extract thoracoabdominal movement parameters （velocity, amplitude, duration of single movement, and frequency）, and differences in movement patterns between the two groups were compared. [Results] ①The YOLOv5s model achieved P values of 98.4% and 98.3% for lying and standing posture recognition, respectively, with a false positive rate <2%, indicating minimal misjudgment risk; R values was 95.3% and 94.6%, with a missed detection rate <6%, demonstrating excellent detection coverage; mAP reached 96.3% and 95.2%, reflecting stable comprehensive performance and strong robustness. ②Optical flow analysis showed that the mean thoracoabdominal movement velocity in Group B was 5.358 px/s, significantly higher than that in Group A （2.461 px/s, P<0.05）; the mean movement amplitude in Group B was 6.104 px, extremely significantly higher than that in Group A （2.280 px, P<0.01）; the mean duration of single movements was 4.687 s in Group B and 4.272 s in Group A, with no significant difference （P=0.35）; Group B showed a significantly higher movement frequency （45.67 times） compared to Group A （12.92 times, P<0.01）, with reduced rhythmicity, indicating that parturition difficulty increases with prolonged parturition duration. [Conclusion] The synergistic application of the YOLOv5s model and Farneback optical flow algorithm enabled precise recognition of parturient dairy goat postures and accurate quantification of thoracoabdominal movements. This technology can be integrated into farm parturition early-warning systems to identify abnormal parturition behaviors in real time, reduce the risk of dystocia, and provide technical support for intelligent dairy goat management.

Key words: dairy goat, thoracoabdominal movement patterns, posture recognition, YOLOv5s model, Farneback optical flow algorithm

中图分类号:

冯思远, 安晓萍, 王园, 齐景伟. 分娩奶山羊躺卧姿态的自动识别及胸腹部运动规律研究[J]. 畜牧与饲料科学, 2025, 46(2): 59-70.

FENG Siyuan, AN Xiaoping, WANG Yuan, QI Jingwei. Automatic Recognition of Lying Postures and Analysis of Thoracoabdominal Movement Patterns in Parturient Dairy Goats[J]. Animal Husbandry and Feed Science, 2025, 46(2): 59-70.

参考文献

[1] MATTHEWS S G, MILLER A L, CLAPP J, et al.Early detection of health and welfare compromises through automated detection of behavioural changes in pigs[J].The Veterinary Journal,2016,217:43-51.
[2] SANTONI M M, SENSUSE D I, ARYMURTHY A M, et al.Cattle race classification using gray level co-occurrence matrix convolutional neural networks[J].Procedia Computer Science,2015,59:493-502.
[3] DOVILE M, RAMŪNAS A, VIDA J, et al. Impact of calving difficulty on lameness in dairy cows[J].Agriculture,2022,12(7):960.
[4] MOREK-KOPEC M, ZARNECKI A, PTAK E, et al.Effect of calving difficulties and calf mortality on functional longevity in Polish Holstein-Friesian cows[J].Animals (Basel),2021,11(10):2792.
[5] VANRADEN P M, COLE J B, GADDIS K L P. Net merit as a measure of lifetime profit:2014 revision[J].AIP Research Report,2018,7:5-18.
[6] SUN S, QIN J, XUE H.Sheep delivery scene detection based on faster-RCNN[C]//2019 International conference on image and video processing, and artificial intelligence.Bellingham,Washington:SPIE,2019,11321:297-303.
[7] LI J, WU J M.Leukocyte detection in blood smear image based on improved YOLOv3[C]//Proceedings of the 2020 the 10^th international workshop on computer science and engineering (WCSE 2020).Shanghai:WCSE 2020,2020:144-149.
[8] LIU W, ANGUELOV D, ERHAN D, et al.SSD: Single shot multibox detector[M]//BASTIAN L, JIRI M, NICU S, et al.Computer vision-ECCV 2016. Cham:Springer International Publishing,2016:21-37.
[9] 代昕,王军号,张翼,等.基于时空流特征融合的俯视视角下奶牛跛行自动检测方法[J].智慧农业,2024,6(4):18-28.
[10] KLIEMANN R D, FERNANDES S R, CAMPOS M M, et al.Sensor validation to record rumination and analysis of behavioral parameters of dairy Gyr heifers in feedlot systems[J].Tropical Animal Health and Production,2023,55(3):166.
[11] BLOCH V, FRONDELIUS L, ARCIDIACONO C, et al.Development and analysis of a CNN- and transfer-learning-based classification model for automated dairy cow feeding behavior recognition from accelerometer data[J].Sensors,2023,23(5):2611.
[12] 吴頔华. 基于视频分析的奶牛呼吸行为检测方法研究[D].杨凌:西北农林科技大学,2021.
[13] 赵凯旋,何东健,王恩泽.基于视频分析的奶牛呼吸频率与异常检测[J].农业机械学报,2014,45(10):258-263.
[14] WU D H, YIN X Q, JIANG B, et al.Detection of the respiratory rate of standing cows by combining the Deeplab V³+ semantic segmentation model with the phase-based video magnification algorithm[J].Biosystems Engineering,2020,192:72-89.
[15] SUN S W,QIN J P,XUE H S.Sheep delivery scene detection based on faster-RCNN[C]//2019 International conference on image,video processing and artificial intelligence.Bellingham,Washinton:SPIE,2019,11321:11321C.
[16] LISEUNE A, VAN DEN POEL D, HUT P R, et al. Leveraging sequential information from multivariate behavioral sensor data to predict the moment of calving in dairy cattle using deep learning[J].Computers and Electronics in Agriculture,2021,191:106566.
[17] BARRIER A C, HASKELL M J, MACRAE A I, et al.Parturition progress and behaviours in dairy cows with calving difficulty[J].Applied Animal Behaviour Science,2012,139(3/4):209-217.
[18] ARTHUR G H, BEE D.Dystocia and other disorders associated with parturition[J].International Journal of Gynecology and Obstetrics,1996,53(1):73-80.
[19] BEAM A L, LOMBARD J E, KOPRAL C A, et al.Prevalence of failure of passive transfer of immunity in newborn heifer calves and associated management practices on US dairy operations[J].Journal of Dairy Science,2009,92(8):3973-3980.
[20] AKBARZADEH M, NEMATOLLAHI A, FARAHMAND M, et al.The effect of two-staged warm compress on the pain duration of first and second labor stages and apgar score in prim gravida women:a randomized clinical trial[J].Journal of Caring Sciences,2018,7(1):21-26.
[21] FREY H A, TUULI M G, CORTEZ S, et al.Does delayed pushing in the second stage of labor impact perinatal outcomes?[J].American Journal of Perinatology,2012,29(10):807-814.
[22] AKBARZADEH M, MORADI Z, HADIANFARDM J,et al.Comparison of the effect of mono-stage and bi- stage acupressure at sp6 point on the severity of labor pain and the delivery outcome[J]. International Journal of Community Based Nursing and Midwifery,2013,1(3):165-172.
[23] REYNOLDS F.The effects of maternal labour analgesia on the fetus[J].Best Practice and Research:Clinical Obstetrics and Gynaecology,2010,24(3):289-302.

编辑推荐 0

Metrics

阅读次数

全文

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	0	0	0	30

来源	本网站	其他网站

次数	29	1
比例	97%	3%

摘要

最新录用	在线预览	正式出版

0	0	11

	来源	本网站

	次数	11
	比例	100%

分娩奶山羊躺卧姿态的自动识别及胸腹部运动规律研究

Automatic Recognition of Lying Postures and Analysis of Thoracoabdominal Movement Patterns in Parturient Dairy Goats

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐 0

Metrics

本文评价

[1]	苏少锋, 孟子琪, 王超, 赵俊利, 郝宸昉, 赵启南. 基于线粒体DNA D-loop区序列分析中国及新西兰奶山羊遗传进化关系[J]. 畜牧与饲料科学, 2022, 43(3): 64-72.
[2]	程明,刘开东,张宝旬,孙友德,李培培,杨培培,王建华,刘宗正. 崂山奶山羊骨髓间充质干细胞永生化细胞系的建立[J]. 畜牧与饲料科学, 2019, 40(1): 11-14.
[3]	辛守帅,张宝旬,刘开东,李培培,杨培培,王建华,刘宗正. 崂山奶山羊永生化骨髓间充质干细胞的诱导分化研究[J]. 畜牧与饲料科学, 2019, 40(1): 1-5.
[4]	刘宗正,肖娜,杨培培,刘开东,李培培,王建华. 崂山奶山羊脂肪间充质干细胞系的建立及鉴定[J]. 畜牧与饲料科学, 2018, 39(12): 1-5.
[5]	孙军昌. 奶山羊产奶性状相关基因的筛选与功能研究进展[J]. 畜牧与饲料科学, 2018, 39(11): 61-65.
[6]	周建雄,黄梅,普光辉. 果园生草养殖奶山羊的畜牧生态化养殖技术探讨[J]. 畜牧与饲料科学, 2018, 39(10): 75-78.
[7]	杨培培,程明,王学梅,刘萌萌,张倩,戴正浩,刘宗正. 崂山奶山羊胎儿骨髓间充质干细胞（BMSCs）的分离培养及成神经诱导分化[J]. 畜牧与饲料科学, 2016, 37(9): 99-99.
[8]	杨斌,凤英,达来宝力格,张月梅,宋爱军,陈伟,兰天驰,金海,赵世华. 奶山羊传染性角膜结膜炎的诊治[J]. 畜牧与饲料科学, 2015, 36(11): 118-118.
[9]	赵航,康南,赵西林. 倾斜复位手术治疗奶山羊产后子宫脱垂[J]. 畜牧与饲料科学, 2014, 35(2): 113-113.
[10]	斯普勒玛. 奶山羊冬季常见疾病及防治措施[J]. 畜牧与饲料科学, 2014, 35(12): 127-127.
[11]	左兆霞. 奶山羊常见病的诊断与防治[J]. 畜牧与饲料科学, 2013, 34(5): 116-116.
[12]	李蕴华. 奶山羊繁殖期管理技术[J]. 畜牧与饲料科学, 2013, 34(3): 70-70.
[13]	王丽芳,卢德勋. 黑沙蒿乙醇粗提物对奶山羊体外试验CLA含量及C_（18）不饱和脂肪酸生物氢化率的影响[J]. 畜牧与饲料科学, 2011, 32(9): 62-62.
[14]	苏和,达来,高娃. 不同药物对奶山羊同期发情的效果研究[J]. 畜牧与饲料科学, 2003, 24(6): 68-68.
[15]	薛志勇. 奶山羊乳房炎的防治[J]. 畜牧与饲料科学, 2003, 24(4): 49-49.